Safe and explainable AI to help doctors with heart disease, sepsis, and breast cancer care
SAFE AND EXPLAINABLE AI-ENABLED DECISION MAKING FOR PERSONALIZED CLINICAL DECISION SUPPORT
This project will try AI tools that give safe, explainable decision support for adults treated for cardiology conditions, sepsis, or invasive breast cancer at Penn Medicine.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 300000 (estimated) |
| Ages | 18 Years and up |
| Sex | All |
| Sponsor | Abramson Cancer Center at Penn Medicine Academic / other |
| Locations | 1 site (Philadelphia, Pennsylvania) |
| Trial ID | NCT06694181 on ClinicalTrials.gov |
What this trial studies
Researchers will develop and validate AI-powered clinical decision support systems using electronic health record data and the Penn Cancer Registry from 2017 onward. The work focuses on integrating medical knowledge into models, making recommendations explainable to clinicians, and building safety guarantees for real-world use. The effort is observational and uses retrospective and prospective data from adult cardiology admissions, sepsis presentations, and invasive breast cancer cases, excluding pediatric patients and certain clinical subgroups (for example cardiac arrest primaries and patients with pre-existing limits on life-sustaining therapy). Models will be tested for predictive performance, transparency of their outputs, and measures intended to reduce unsafe or misleading recommendations.
Who should consider this trial
Good fit: Adults (age 18 or older) who were treated at Penn Medicine hospitals since 2017 and who meet the study cohorts for cardiology admissions, sepsis presentations, or invasive breast cancer in the Penn Cancer Registry are the intended participants.
Not a fit: Patients under 18, people treated outside Penn Medicine, and certain subgroups such as cardiology patients admitted for primary cardiac arrest or sepsis patients with pre-existing limits on life-sustaining therapy are unlikely to be included or to benefit from the models developed here.
Why it matters
Potential benefit: If successful, this could help clinicians make safer, more transparent decisions, reduce avoidable errors, and personalize care for adults with cardiac conditions, sepsis, or breast cancer.
How similar studies have performed: Previous work on explainable AI and clinical decision support has shown promise in retrospective and limited prospective settings, but broad safety guarantees and consistent real-world benefit remain incompletely demonstrated.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: Cardiology 18 years of age and older, admitted to any of the Penn Medicine hospitals from 2017 to the present. Sepsis 18 years of age at the time of presentation to an emergency department or admission to any Penn Medicine hospital from July 1, 2017, onward will be eligible as this represents the population at risk for acquiring sepsis Oncology 18 years of age and older with a diagnosis of invasive breast cancer (Stage 1-4) in the Penn Cancer registry Exclusion Criteria All prediction models will exclude patients under the age of 18 from their patient data sets. Cardiology Patients whose primary admission diagnosis was cardiac arrest Sepsis Those with pre-existing limitations on life-sustaining therapy will be excluded because their eligibility for sepsis definitions, care received, and outcomes, may be significantly and variably affected by pre-existing limitations on care. Oncology There are no other exclusions.
Where this trial is running
Philadelphia, Pennsylvania
- Hospital of the University of Pennsylvania — Philadelphia, Pennsylvania, United States (Recruiting)
Study contacts
- Study coordinator: Haideliza Soto Calderon
- Email: haideliza.soto-calderon@pennmedicine.upenn.edu
- Phone: 215-220-9425
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.